Triple
T14631009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Very Bad Things |
E343476
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Kobe Tai
Kobe Tai is an American former adult film actress who gained mainstream visibility through a small role in the dark comedy film "Very Bad Things."
|
E1110479
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kobe Tai | Statement: [Very Bad Things, castMember, Kobe Tai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kobe Tai Context triple: [Very Bad Things, castMember, Kobe Tai]
-
A.
Kobe Kachoen
Kobe Kachoen is a popular interactive animal and flower park in Kobe, Japan, known for its close-up encounters with birds and other animals amid extensive indoor botanical displays.
-
B.
Goro
Goro is a four-armed Shokan prince and powerful sub-boss character from the Mortal Kombat fighting game series.
-
C.
Goro
Goro is a town located in the Bale Zone of the Oromia Region in southeastern Ethiopia.
-
D.
Goro
Goro is a coastal fishing town and municipality in Italy’s Emilia-Romagna region, known for its clam and mussel production along the Po River delta.
-
E.
Kokonoe
Kokonoe is a small mountainous town in Japan known for its hot springs, scenic highlands, and suspension bridges.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kobe Tai Triple: [Very Bad Things, castMember, Kobe Tai]
Generated description
Kobe Tai is an American former adult film actress who gained mainstream visibility through a small role in the dark comedy film "Very Bad Things."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kobe Tai Target entity description: Kobe Tai is an American former adult film actress who gained mainstream visibility through a small role in the dark comedy film "Very Bad Things."
-
A.
Kobe Kachoen
Kobe Kachoen is a popular interactive animal and flower park in Kobe, Japan, known for its close-up encounters with birds and other animals amid extensive indoor botanical displays.
-
B.
Goro
Goro is a four-armed Shokan prince and powerful sub-boss character from the Mortal Kombat fighting game series.
-
C.
Goro
Goro is a town located in the Bale Zone of the Oromia Region in southeastern Ethiopia.
-
D.
Goro
Goro is a coastal fishing town and municipality in Italy’s Emilia-Romagna region, known for its clam and mussel production along the Po River delta.
-
E.
Kokonoe
Kokonoe is a small mountainous town in Japan known for its hot springs, scenic highlands, and suspension bridges.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d822dffc3c8190aa173b90761bffda |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4a912248190a3df7f821395c776 |
completed | April 14, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda931834081909d90ec0479eca3f9 |
completed | May 8, 2026, 9:13 a.m. |
| NEDg | Description generation | batch_69fdb27c8db481909330d299faded4f3 |
completed | May 8, 2026, 9:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdb3b24320819098dd7fab0c3a0507 |
completed | May 8, 2026, 9:58 a.m. |
Created at: April 10, 2026, 1:26 a.m.